Air pollution causes widespread environmental and health problems and severely hinders the quality of life of urban residents. Traffic is critical for human life, but its emissions are a major source of pollution, aggravating urban air pollution. However, the complex interaction between traffic emissions and air pollution in cities and regions has not yet been revealed. In particular, the spread of COVID-19 has led various cities and regions to implement different traffic restriction policies according to the local epidemic situation, which provides the possibility to explore the relationship between urban traffic and air pollution. Here, we explore the influence of traffic on air pollution by reconstructing a multi-layer complex network base on the traffic index and air quality index. We uncover that air quality in the Beijing–Tianjin–Hebei (BTH), Chengdu–Chongqing Economic Circle (CCS), and Central China (CC) regions is significantly influenced by the surrounding traffic conditions after the outbreak. Under different stages of the fight against the epidemic, the influence of traffic in some regions on air pollution reaches the maximum in stage 2 (also called Initial Progress in Containing the Virus). For the BTH and CC regions, the impact of traffic on air quality becomes bigger in the first two stages and then decreases, while for CC, a significant impact occurs in phase 3 among the other regions. For other regions in the country, however, the changes are not evident. Our presented network-based framework provides a new perspective in the field of transportation and environment and may be helpful in guiding the government to formulate air pollution mitigation and traffic restriction policies.

In recent years, more and more researchers have focused on emotion recognition methods based on electroencephalogram (EEG) signals. However, most studies only consider the spatio-temporal characteristics of EEG and the modelling based on this feature, without considering personality factors, let alone studying the potential correlation between different subjects. Considering the particularity of emotions, different individuals may have different subjective responses to the same physical stimulus. Therefore, emotion recognition methods based on EEG signals should tend to be personalized. This paper models the personalized EEG emotion recognition from the macro and micro levels. At the macro level, we use personality characteristics to classify the individuals’ personalities from the perspective of ‘birds of a feather flock together’. At the micro level, we employ deep learning models to extract the spatio-temporal feature information of EEG. To evaluate the effectiveness of our method, we conduct an EEG emotion recognition experiment on the ASCERTAIN dataset. Our experimental results demonstrate that the recognition accuracy of our proposed method is 72.4% and 75.9% on valence and arousal, respectively, which is 10.2% and 9.1% higher than that of no consideration of personalization.

City taxi service systems have been empirically studied by a number of data-driven methods. However, their underlying mechanisms are hard to understand because the present mathematical models neglect to explain a (whole) taxi service process that includes a pair of on-load phase and off-load phase. In this paper, by analyzing a large amount of taxi servicing data from a large city in China, we observe that the taxi service process shows different temporal and spatial features according to the on-load phase and off-load phase. Moreover, our correlation analysis results demonstrate the lack of dependence between the on-load phase and the off-load phase. Hence, we introduce two independent random walk models based on the Langevin equation to describe the underlying mechanism and to understand the temporal and spatial features of the taxi service process. Our study attempts to formulate the mathematical framework for simulating the taxi service process and better understanding of its underlying mechanism.

In research on complex networks, mining relatively important nodes is a challenging and practical work. However, little research has been done on mining relatively important nodes in complex networks, and the existing relatively important node mining algorithms cannot take into account the indicators of both precision and applicability. Aiming at the scarcity of relatively important node mining algorithms and the limitations of existing algorithms, this paper proposes a relatively important node mining method based on distance distribution and multi-index fusion (DDMF). First, the distance distribution of each node is generated according to the shortest path between nodes in the network; then, the cosine similarity, Euclidean distance and relative entropy are fused, and the entropy weight method is used to calculate the weights of different indexes; Finally, by calculating the relative importance score of nodes in the network, the relatively important nodes are mined. Through verification and analysis on real network datasets in different fields, the results show that the DDMF method outperforms other relatively important node mining algorithms in precision, recall, and AUC value.